RMB exchange rate forecasting algorithm and empirical analysis

DOI

10.2991/978-94-6463-262-0_12How to use a DOI?

Keywords

RMB Exchange Rate Forecast; CEEMDAN decomposition; ARIMA time series; BP neural network; LSTM neural network

Abstract

This paper studies the forecasting algorithm of RMB exchange rate. Firstly, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise algorithm (CEEMDAN) is used to decompose the exchange rate data into several intrinsic mode functions (IMF). Then the correlation coefficients of each IMF are calculated, and the high-frequency components with low correlation are regarded as noisy signals for filtering. The low frequency IMF components are forecast by Autoregressive Integrated Moving Average Model (ARIMA) time series model, while the high frequency IMF components are predicted by BP neural network model and Long Short Term Memory (LSTM) neural network model. Finally, the predicted values of each component are added to construct a new forecasting algorithm for the RMB exchange rate. In the empirical analysis, we collected the exchange rate data of RMB against US dollar and RMB against EUR every working day (FOREX opening hours Beijing time. Monday to Friday) from January 2, 2019 to December 22, 2022, and carry out empirical analysis of the exchange rate from December 23, 2022 to January 20, 2023 by using the prediction algorithm constructed in this paper. By comparing with the true value (the true exchange rate value published by FOREX), the average forecast error is 0.1779 % (RMB/USD) and 0.2072 % (RMB/EUR) respectively. It should be emphasized that our forecasting method can more precisely predict the RMB exchange rate over four weeks, which provides sufficient buffer time for the foreign exchange management department to conduct supervision and formulate countermeasures.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ruoxi Gu
AU  - Yongqi Du
AU  - Shaohua Guo
AU  - Zhuofan Zhang
AU  - Kaisu Wu
PY  - 2023
DA  - 2023/10/09
TI  - RMB exchange rate forecasting algorithm and empirical analysis
BT  - Proceedings of the 3rd International Conference on Management Science and Software Engineering (ICMSSE 2023)
PB  - Atlantis Press
SP  - 96
EP  - 104
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-262-0_12
DO  - 10.2991/978-94-6463-262-0_12
ID  - Gu2023
ER  -